Mercurial > hg > extraction-interface
diff models/extractapp.php @ 47:886f43b26ee2 extractapp
move/remove develop folder
| author | Zoe Hong <zhong@mpiwg-berlin.mpg.de> |
|---|---|
| date | Tue, 17 Mar 2015 10:54:13 +0100 |
| parents | |
| children | c98a0c6d7eb4 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/models/extractapp.php Tue Mar 17 10:54:13 2015 +0100 @@ -0,0 +1,1343 @@ + + +<?php + +class ExtractappModel extends BaseModel{ + + public function Index() { + return array("Index Value 1", "Value 2", "Value 3"); + } + + protected $section_id = 0, $data_path, $file_id = 0, $current_fileId=0, + $branch_id = 0, $user_id = 0, $lg_text = "", $topic, $taglist_infile = "", $book_meta = ""; + public $messages = ""; + + private function Initialize($_urlvalues) { + $this->SetSectionId($_urlvalues); + + } + + public function GetTextFromFileId($_postdata) { + $this->file_id = $_postdata['fileId']; + $branch_id = $_postdata['branchId']; + $section_id = $_postdata['sectionId']; + + $this->branch_id = $branch_id; + $this->user_id = $_postdata['userId']; + $this->section_id = $section_id; + + $this->section_name = $_postdata['sectionName']; + $this->book_id = $_postdata['bookId']; + $this->book_name = $_postdata['bookName']; + + // get from URL with file_id + $lg_text_url = $this->get_text_from_fileId_url.$this->file_id; + //$lg_text = file_get_contents($lg_text_url); + // --- parsing meta data + $lg_text = $this->ParseMetaData($lg_text_url); + + // ---- + + + $stringInput = $lg_text; + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + $lg_text = $stringInput; + + $this->lg_text = $lg_text; + + } + + public function GetTextFromSectionId($_postdata) { + $section_id = $_postdata['sectionId']; + $this->section_id = $section_id; + $this->user_id = $_postdata['userId']; + + $this->section_name = $_postdata['sectionName']; + $this->book_id = $_postdata['bookId']; + $this->book_name = $_postdata['bookName']; + + // get from URL with file_id + $lg_text_url = $this->get_text_from_sectionId_url.$section_id; + $lg_text = file_get_contents($lg_text_url); + + $stringInput = $lg_text; + $stringInput = preg_replace("/<(.*?)>/u", "○", $stringInput); + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + $lg_text = $stringInput; + + $this->lg_text = $lg_text; + } + + public function GetTextFromLocal($_id){ + $this->section_id = $_id; + $this->messages .= "DEBUG: from my local"."<br>"; + $this->lg_text = $this->GetSectionContent(); + + } + + public function GetInfoFromPreviousPage($_postdata) { + + if ($_postdata['fileId']) { + $this->file_id = $_postdata['fileId']; + } + if ($_postdata['sectionId']) { + $this->section_id = $_postdata['sectionId']; + } + if ($_postdata['text']) { + $this->lg_text = $_postdata['text']; + } + if ($_postdata['branchId']) { + $this->branch_id = $_postdata['branchId']; + } + if ($_postdata['userId']) { + $this->user_id = $_postdata['userId']; + } + if ($_postdata['topic_id']) { + $this->topic = $_postdata['topic_id']; + } + + if ($_postdata['sectionName']) { + $this->section_name = $_postdata['sectionName']; + } + if ($_postdata['bookName']) { + $this->book_name = $_postdata['bookName']; + } + if ($_postdata['bookId']) { + $this->book_id = $_postdata['bookId']; + } + if ($_postdata['currentFileId']) { + $this->current_fileId = $_postdata['currentFileId']; + } + if ($_postdata['taglistArray']) { + $this->taglist_infile = json_decode($_postdata['taglistArray']); + } + if ($_postdata['book_meta']) { + $this->book_meta = json_decode($_postdata['book_meta']); + } + + } + public function InitData($_postdata) { + $file_id = $_postdata['fileId']; + $branch_id = $_postdata['branchId']; + $section_id = $_postdata['sectionId']; + + $this->branch_id = $branch_id; + $this->file_id = $file_id; + $this->user_id = $_postdata['userId']; + $this->section_id = $section_id; + + if ($file_id != 0 && $branch_id != 0) { + // get from URL with file_id + $lg_text_url = $this->get_text_from_fileId_url.$file_id; + } else if ($section_id != 0) { + // get from URL with section_id + $lg_text_url = $this->get_text_from_sectionId_url.$section_id; + } else { + echo "wrong url!!"; + return; + } + + + $lg_text = file_get_contents($lg_text_url); + + /* + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + */ + + // the text is from database + $stringInput = $lg_text; + $stringInput = preg_replace("/<(.*?)>/u", "○", $stringInput); + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + $lg_text = $stringInput; + + $this->lg_text = $lg_text; + + + } + /* + public function Reload($_postdata) { + + // update text using $this->current_fileId + // getTextbyFileId + $current_fileId = $_postdata['currentFileId']; + //$this->file_id = $_postdata['currentFileId']; + //$this->GetTextFromFileId($_postdata); + //$latest_editing = $this->lg_text; + // get from URL with file_id + + $lg_text_url = $this->get_text_from_fileId_url.$current_fileId; + $lg_text = file_get_contents($lg_text_url); + + $stringInput = $lg_text; + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + $lg_text = $stringInput; + + + //var_dump($lg_text); + + echo json_encode($lg_text); + //var_dump($this->file_id); + + } + */ + + + // TODO: comparison not correct + private function Taglist_infileUpToDate($taglistArray) { + // compare $this->taglist_infile is the same as $taglistArray + $taglist_infile = $this->taglist_infile; + if (count($taglist_infile) != count($taglistArray)) { + return false; + } + + foreach ($taglistArray as $row_indb) { + $cnt = 0; + foreach ($taglist_infile as $row) { + //$taglistArray: array( $row['id'], $row['name'], $row['tag'], $row['color'] ) + if ($row[0] == $row_indb[0] && $row[1] == $row_indb[1] && $row[2] == $row_indb[2] && $row[3] == $row_indb[3]) { + + } else { + $cnt ++; + } + } + if ($cnt == count($row)) { + return false; + } + } + return true; + } + // === for tagging === + public function StartTagging() { + + $section_id = $this->section_id; + $stringInput = $this->lg_text; + + $data = array(); // data array to be passed to view + + //$taglistArray = $this->GetTaglistArray(); + //for GetTaglistByTopicID: + $taglistArray = $this->GetTaglistByTopicID($this->GetTopic()); + + $data['taglist_infile'] = $this->taglist_infile; + // TODO: check if taglist_infile is up-to-date + /* + if ( !$this->Taglist_infileUpToDate($taglistArray)) { + $data['taglist_infile'] = $this->taglist_infile; + } else { + $data['taglist_infile'] = ""; + } + */ + + // book_meta + $data['book_meta'] = $this->book_meta; + + // topic list + $topiclistArray = $this->GetTopiclistArray(); + + + $wordlistArray = $this->GetWordlistArray(); + + $data['stringInput'] = $stringInput; + $data['taglistArray'] = $taglistArray; + $data['wordlistArray'] = $wordlistArray; + $data['section_id'] = $section_id; + $data['topiclistArray'] = $topiclistArray; + $data['default_topic_id'] = $this->GetTopic(); + $data['topic_tag'] = $this->GetTopicTag($this->GetTopic()); + $data['topic_name'] = $this->GetTopicName($this->GetTopic()); + + + $data['info'] = array('file_id'=>$this->file_id, 'user_id'=>$this->user_id, + 'branch_id'=>$this->branch_id, 'section_id'=>$this->section_id, 'book_id'=>$this->book_id, + 'book_name'=>$this->book_name, 'section_name'=>$this->section_name, + 'current_fileId'=>$this->current_fileId); + //'current_fileId'=>$this->file_id); + //'current_fileId'=>'123'); + + $this->messages .= "Info: "; + $this->messages .= "file_id=".$this->file_id.", section_id=".$this->section_id; + $this->messages .= ", user_id=".$this->user_id.", branch_id=".$this->branch_id.", topic_id=".$this->topic; + $this->messages .= ", book_id=".$this->book_id.", book_name=".$this->book_name.", section_name=".$this->section_name; + $this->messages .= ", current_fileId=".$this->current_fileId."<br>"; + + $data['messages'] = $this->messages; + + return $data; + + } + + public function SaveFullText($postdata) { + if ($postdata['text']){ + $date = date('Y_m_d_H_i_s', time()); + if ( file_exists("data/parsing_files/".$postdata['filename'].".txt") ) { + $oldFile = file_get_contents("data/parsing_files/".$postdata['filename'].".txt"); + file_put_contents("data/parsing_files/".$postdata['filename']."_".$date.".txt", $oldFile); + } + + if (get_magic_quotes_gpc()) { + $require = stripslashes($postdata['text']); + } else { + $require = $postdata['text']; + } + + $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require); + $require = preg_replace('/&/u', "&", $require); + $require = preg_replace("/○/u", " ", $require); + $require = preg_replace("/<br>/u", "\n", $require); + $require = preg_replace("/<br>/u", "\n", $require); + file_put_contents("data/parsing_files/".$postdata['filename'].".txt", $require); + } + + } + + public function UpdateInfoByResponseFromLGService($response) { + + /* + $response_file = $response["file"]; + $response_branch = $response["branch"]; + + + $status = (string)$response["status"]; + + if ((string)$response["status"] == "error") { + $response_currentFile = $response["currentFile"]; + + $this->current_fileId = (string)$response_currentFile['id']; + $this->messages .= "saving does not success! ".(string)$response["message"]; + + + } else { + + $this->messages .= "saving success."; + var_dump((string)$response_file["id"]); + + $this->file_id = (string)$response_file["id"]; + $this->branch_id = (string)$response_branch["id"]; + + } + */ + + + $response_file = $response["file"]; + $response_branch = $response["branch"]; + + $status = (string)$response["status"]; + if ($status == "ok") { + $this->messages .= "saving success."; + $this->file_id = (string)$response_file["id"]; + $this->branch_id = (string)$response_branch["id"]; + + } else if ($status == "error") { + // saving not success + $this->messages .= "saving does not success! ".(string)$response["message"]; + $response_currentFile = $response["currentFile"]; + //$this->current_fileId = $response["currentFileId"]; + $this->current_fileId = (string)$response_currentFile["id"]; + + } + + + } + private function AppendMetaData($text_content) { + $text = '<?xml version="1.0" encoding="UTF-8"?>'; + $text .= "\n<text>\n"; + // topic + $text .= "<topic>".$this->topic."</topic>\n"; + // book meta data + $book = $this->book_meta; + foreach ($book as $b) { + $text .= "<book>\n"; + $text .= "<title>".$b[0]."</title>\n"; + $text .= "<author>".$b[1]."</author>\n"; + $text .= "<year>".$b[2]."</year>\n"; + $text .= "<pagenumber>".$b[3]."</pagenumber>\n"; + $text .= "</book>\n"; + } + // taglist + $taglist = $this->taglist_infile; + foreach ($taglist as $tagitem) { + $text .= "<tagitem>\n"; + $text .= "<id>".$tagitem[0]."</id>\n"; + $text .= "<name>".$tagitem[1]."</name>\n"; + $text .= "<tag>".$tagitem[2]."</tag>\n"; + $text .= "<color>".$tagitem[3]."</color>\n"; + $text .= "</tagitem>\n"; + } + + // text_content + $text .= $text_content; + $text .= "\n</text>"; + + return $text; + } + public function SaveFullTextToLGService($_postdata) { + // save tagged text (full text) by Jorge's API to lg service + + // -------- + if ($_postdata['text']){ + $date = date('Y_m_d_H_i_s', time()); + if ( file_exists("data/parsing_files/".$_postdata['sectionId'].".txt") ) { + $oldFile = file_get_contents("data/parsing_files/".$_postdata['sectionId'].".txt"); + //saving in my local machine in developing phrase + file_put_contents("data/parsing_files/".$_postdata['sectionId']."_".$date.".txt", $oldFile); + } + + if (get_magic_quotes_gpc()) { + $require = stripslashes($_postdata['text']); + } else { + $require = $_postdata['text']; + } + + $require = preg_replace("/【<a(.*?)>(.*?)<\/a>】/u", "【\\2】", $require); + $require = preg_replace('/&/u', "&", $require); + $require = preg_replace("/○/u", " ", $require); + $require = preg_replace("/<br>/u", "\n", $require); + //$require = preg_replace("/<br>/u", "\n", $require); + + if ($_postdata['branchId'] == 0) { + // -- new branch case + $require = "<text_content>\n".$require."</text_content>\n"; + } + $require = $this->AppendMetaData($require); + + //saving in my local machine in developing phrase + file_put_contents("data/parsing_files/".$_postdata['sectionId'].".txt", $require); + } + + // ------ + + + if ($_postdata['branchId'] != 0) { + // -- exiting branch case + $postfields = array( + "text" => $require, + "branchId" => $_postdata['branchId'], + "userId" => $_postdata['userId'], + "userPreviousFileId" => $_postdata['fileId'], + ); + $save_url = $this->save_to_LGService_url; + + } else { + // -- new branch case + echo "saveNew!"; + $user_id = "0"; + if ($_postdata['userId']) { + $user_id = $_postdata['userId']; + } + + $postfields = array( + "text" => $require, + "sectionId" => $_postdata['sectionId'], + "userId" => $user_id, + "label" => $_postdata['label'], + ); + $save_url = $this->save_new_to_LGService_url; + } + + + // set up the curl resource + $ch = curl_init(); + curl_setopt($ch, CURLOPT_URL, $save_url); + curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); + curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST"); + curl_setopt($ch, CURLOPT_POST, true); + curl_setopt($ch, CURLOPT_POSTFIELDS, $postfields); + //curl_setopt($ch, CURLOPT_HEADER, true); + curl_setopt($ch, CURLOPT_HTTPHEADER, array( + 'Content-type: multipart/form-data;charset=utf-8' + )); + + // execute the request + // **** commended to DEBUG *** + //$output = curl_exec($ch); + // ***** + + // output the profile information - includes the header + //echo($output) . PHP_EOL; + + // close curl resource to free up system resources + curl_close($ch); + + $response = json_decode($output, true); + return $response; + + } + + // --- for regex ---- + public function GetRegexFilenameById($topic_id) { + $query = sprintf("SELECT regex_filename FROM `topic_regex_relation` WHERE topic_id=\"%s\"", $topic_id); + $result = mysql_query($query); + if (!$result) { + return json_encode("Failed during selecting topic_regex_relation table."); + } + + $filenames = array(); + while ($row = mysql_fetch_assoc($result)) { + array_push($filenames, $row['regex_filename']); + } + + return $filenames; + } + public function SmartRegexLoad($topic_id) { + + // Load regex file based on current topic. Only shows the regex in this topic -- + $filenames = $this->GetRegexFilenameById($topic_id); + + // Get regex file from filesystem ---- + $data_path = "./data/"; // get the current file path, which is getcwd(), and concatenate with "/data/" + $returnArray = array(); + $files1 = scandir($data_path."regex_files"); + foreach ( $files1 as $file ) { + if ( $file != "." && $file != ".." && $file != ".DS_Store") { + foreach ($filenames as $filename) { + if ($file == $filename) { + $returnArray[preg_replace("/\.txt/", "", $file)] = file_get_contents( $data_path."regex_files/".$file ); + break; + } + } + } + } + echo json_encode($returnArray); + return; + } + + + public function SmartRegexSave($_postdata) { + if ($_postdata['text']){ + + // --- update topic_regex_relation table --- + $topic_id = $_postdata['topic_id']; + $filename = $_postdata['filename'].'.txt'; + + // check if already existing a record for this regex file + $query = "SELECT * FROM topic_regex_relation WHERE topic_id=".$topic_id." AND regex_filename='".$filename."'"; + $result = mysql_query($query); + if (!$result) { + echo json_encode("ErrorDB"); + } + while ($row = mysql_fetch_assoc($result)) { + if ($row && !$_postdata['forcesave']) { + // promt user a comfirm to force saving or not + echo json_encode("ForceSave"); + return; + } + } + + + if (!$_postdata['forcesave']) { + $query = "INSERT INTO topic_regex_relation (topic_id, regex_filename) VALUES (".$topic_id.",'".$filename."')"; + $result = mysql_query($query); + if (!$result) { + echo json_encode("ErrorDB"); + } + } + // --- write to filesystem --- + + /* + $date = date('Y_m_d_H_i_s', time()); + if ( file_exists("regex_files/".$_POST['filename'].".txt") ) { + $oldFile = file_get_contents("regex_files/".$_POST['filename'].".txt"); + file_put_contents("regex_files/".$_POST['filename']."_".$date.".txt", $oldFile); + } + */ + $data_path = "./data/"; // get the current file path, which is getcwd(), and concatenate with "/data/" + + if (get_magic_quotes_gpc()) { + $require = stripslashes($_postdata['text']); + } else { + $require = $_postdata['text']; + } + + file_put_contents( $data_path."regex_files/".$_postdata['filename'].".txt", $require); + + + } + } + + + // === for export table === + public function ExportTable($postdata) { + // $this->Initialize($urlvalues); + + $content = $postdata['content']; + $topic = $postdata['topic']; + $section_id = $postdata['sectionId']; + + //$section_id = $this->section_id; + + + // TODO: this should be get from LGService: sectionName, bookId, bookName + $sectionName = $postdata['sectionName']; + $bookId = $postdata['bookId']; + $bookName = $postdata['bookName']; + + + // --- replace if get info from LGService + /* + $section_info = $this->GetSectionInfo(); + + $sectionName = $section_info['sectionName']; + $bookId = $section_info['bookId']; + + $books_info = $this->GetBooksInfo($bookId); + $bookName = $books_info['bookName']; + */ + // ===== + + + $outputTableArray = array(); + + //$taglistArray = $this->GetTaglistArray(); + $taglistArray = $this->GetTaglistByTopicID($topic); + + $outputTableArray[0]=array(); + $outputTableArray[0][0]=array(); + $outputTableArray[0][1]=array(); + foreach ( $taglistArray as $value ) { + $outputTableArray[0][0][$value[2]] = $value[1]; + $outputTableArray[0][1][$value[2]] = $value[1]."(Title)"; + } + $outputTableArray[0]["other"] = "其他"; + $outputTableArray[0]["page"] = "頁數"; + $outputTableArray[0]["full"] = "全文"; + + foreach ( $taglistArray as $tagValue ) { + $content = preg_replace("/<\/".$tagValue[2].">○*<".$tagValue[2].">/u", "", $content); + $content = preg_replace("/<".$tagValue[2].">[ ]*<\/".$tagValue[2].">/u", "", $content); + } + + $contentLineArray = explode( "<br>", $content ); + + $count=0; + $pageNow=NULL; + foreach ( $contentLineArray as $value ) { + $count++; + $recordString = $value; + $otherString = $recordString; + //echo $recordString."<br>\n"; + if ( preg_match("/【<a(.*?)>(.*?)<\/a>】/u", $recordString, $matches) ) { + $pageNow = $matches[2]; + } + foreach ( $taglistArray as $tagValue ) { + if ( preg_match_all("/<".$tagValue[2].">(.*?)<\/".$tagValue[2].">/u", $recordString, $matches, PREG_SET_ORDER) ) { + foreach ( $matches as $matchesValue ) { + $matchesValue[1] = preg_replace("/○/u", "", $matchesValue[1]); + if ( preg_match_all("/〈(.*?)〉/u", $matchesValue[1], $matches2, PREG_SET_ORDER) ) { + foreach ( $matches2 as $matches2Value ) { + if ( isset($outputTableArray[$count][0][$tagValue[2]]) ) { + $outputTableArray[$count][0][$tagValue[2]] .= ";".$matches2Value[1]; + } else { + $outputTableArray[$count][0][$tagValue[2]] = $matches2Value[1]; + } + } + } else { + if ( isset($outputTableArray[$count][0][$tagValue[2]]) ) { + $outputTableArray[$count][0][$tagValue[2]] .= ";".$matchesValue[1]; + } else { + $outputTableArray[$count][0][$tagValue[2]] = $matchesValue[1]; + } + } + } + $otherString = preg_replace("/<".$tagValue[2].">(.*?)<\/".$tagValue[2].">/u", " ", $otherString); + } + } + $otherString = preg_replace("/○/u", "", $otherString); + $outputTableArray[$count]["other"] = $otherString; + $outputTableArray[$count]["page"] = $pageNow; + $value = preg_replace("/>/u", ">", $value); + $value = preg_replace("/</u", "<", $value); + $outputTableArray[$count]["full"] = $value; + } + /* + echo "<br>"."DEBUG: outputTableArray:"."<br>"; + var_dump($outputTableArray); + */ + + $topic_tag = $this->GetTopicTag($topic); + + foreach ( $outputTableArray as $arrayIndex => $arrayValue ) { + // output each row which the topic tag + // e.g. the original version is for 'person' + if ( !isset($arrayValue[0][$topic_tag]) ) { + unset($outputTableArray[$arrayIndex]); + } + + /* + if ($topic == 1) { + if ( !isset($arrayValue[0]["person"]) ) { + unset($outputTableArray[$arrayIndex]); + } + } else if ($topic == 2) { + + // for object topic + if ( !isset($arrayValue[0]["object"]) ) { // only the record with the tag of 'object' will become a row + unset($outputTableArray[$arrayIndex]); + } + } + */ + + } + + $data = array(); + + $data['outputTableArray'] = $outputTableArray; + $data['bookId'] = $bookId; + $data['section_id'] = $section_id; + $data['bookName'] = $bookName; + $data['sectionName'] = $sectionName; + + return $data; + + } + + // === for manage tag list === + public function EditTaglist($_postdata) { + $query = "SELECT AUTO_INCREMENT FROM INFORMATION_SCHEMA.TABLES WHERE TABLE_NAME='taglist'"; + $result = mysql_query($query); + if (!$result) { + echo json_encode(mysql_error()); + } + $row = mysql_fetch_assoc($result); + $largest_id = $row['AUTO_INCREMENT']; + + + $topic_id = $_postdata['topic_id']; + $result = $this->GetTaglistByTopicID($topic_id); + + $taglistArray = array(); + + foreach ($result as $row) { + $taglistArray[$row[0]] = array($row[1], $row[2], $row[3]); + //$taglistArray[$row['id']] = array($row['name'], $row['tag'], $row['color']); + // TODO: the format is not good, so I use $row[0], $row[1],... This could be changed some time. + } + + $topic_tag_name = $this->GetTopicTag($topic_id); + + $query = "SELECT id FROM taglist WHERE taglist.tag='".$topic_tag_name."'"; + $result = mysql_query($query); + if (!$result) { + echo json_encode(mysql_error()); + } + $row = mysql_fetch_assoc($result); + $topic_tag_id = $row['id']; + + $data = array(); + $data['taglistArray'] = $taglistArray; + $data['topic_id'] = $topic_id; + $data['largest_id'] = $largest_id; + $data['topic_tag_id'] = $topic_tag_id; + + + return $data; + + } + + private function _GetTag($_postdata) { + if (get_magic_quotes_gpc()) { + $id = stripslashes($_postdata['id']); + $name = stripslashes($_postdata['name']); + $tag = stripslashes($_postdata['tag']); + $color = stripslashes($_postdata['color']); + } else { + $id = $_postdata['id']; + $name = $_postdata['name']; + $tag = $_postdata['tag']; + $color = $_postdata['color']; + } + return array($id, $name, $tag, $color); + } + + public function NewTagElement($postdata) { + if ($postdata['id']){ + list($id, $name, $tag, $color) = $this->_GetTag($postdata); + + $query1 = sprintf("INSERT INTO `taglist` (`id`, `name`, `tag`, `color`, `systemName`) VALUES (%s, %s, %s, %s, %s)", + $this->GetSQLValueString($id, "int"), + $this->GetSQLValueString($name, "text"), + $this->GetSQLValueString($tag, "text"), + $this->GetSQLValueString($color, "text"), + $this->GetSQLValueString($this->systemNAME, "text")); + $result1 = mysql_query($query1); + + + // add it to topic_tag_relation table + $topic_id = $postdata['topic_id']; + + // tag_id is $id; + $query = sprintf("INSERT INTO `topic_tag_relation` (`topic_id`,`tag_id`) VALUES (%s,%s)", $topic_id, $id); + $result = mysql_query($query); + if (!$result) { + echo json_encode("error when insert into topic_tag_relation table"); + } + } + + } + + public function SaveTagElement($postdata) { + if ($postdata['id']){ + list($id, $name, $tag, $color) = $this->_GetTag($postdata); + + $query = sprintf("UPDATE taglist SET `name`=%s, `tag`=%s, `color`=%s WHERE `id`=%s", + $this->GetSQLValueString($name, "text"), + $this->GetSQLValueString($tag, "text"), + $this->GetSQLValueString($color, "text"), + $this->GetSQLValueString($id, "int")); + $result = mysql_query($query); + + } + + } + + public function DeleteTag($postdata) { + if ($postdata['id']) { + $queryInsert = sprintf("DELETE FROM `taglist` WHERE `id` = %s", stripslashes($postdata['id'])); + $resultInsert = mysql_query($queryInsert); + } + + } + + // === for config topic === + public function ConfigTagsInTopic($postdata) { + $topic = $postdata['topic']; + $result = $this->GetTopicByID($topic); + $row = mysql_fetch_assoc($result); + $topic_name = $row['name']; + + /* + $query = "SELECT taglist.*, topic_tag_relation.topic_id FROM taglist LEFT JOIN topic_tag_relation ON taglist.id = topic_tag_relation.tag_id ORDER BY `topic_id`"; + $result = mysql_query($query); + if (!$result) { + return json_encode("Failed during selecting/joining taglist and topic_tag_relation table."); + } + $taglistArray = array(); + while ($row = mysql_fetch_assoc($result)) { + array_push($taglistArray, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id']) ); + } + */ + + // ------ + $query = "SELECT taglist.*, topic_tag_relation.topic_id FROM taglist LEFT JOIN topic_tag_relation ON taglist.id = topic_tag_relation.tag_id ORDER BY `topic_id`"; + $result = mysql_query($query); + if (!$result) { + return json_encode("Failed during selecting/joining taglist and topic_tag_relation table."); + } + + $tag_intopic = array(); + $tag_others = array(); + $tag_tmp_others = array(); + while ($row = mysql_fetch_assoc($result)) { + if ($row['topic_id'] == $topic) { + array_push($tag_intopic, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id'])); + } else { + array_push($tag_tmp_others, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id'])); + } + } + + // --- check if there's any duplicated tags in tag_tmp_others. remove the duplicated tags + $num_others = count($tag_tmp_others); + for ($i=0; $i < $num_others; $i++) { + $cnt = 0; + for ($j=$i+1; $j < $num_others; $j++) { + if ($tag_tmp_others[$i]['tag'] == $tag_tmp_others[$j]['tag']) { + break; + } else { + $cnt++; + } + } + if ($cnt == ($num_others-$i-1) ) { + $row = $tag_tmp_others[$i]; + array_push($tag_others, array('id'=>$row['id'],'name'=>$row['name'], 'tag'=>$row['tag'], 'color'=>$row['color'], 'topic_id'=>$row['topic_id']) ); + } + } + + // --- remove duplicated tags in tag_others that is duplicated with tags in tag_intopic + $tag_tmp_others = $tag_others; + $tag_others = array(); + + foreach ($tag_tmp_others as $tmp) { + $cnt = 0; + foreach ($tag_intopic as $intopic) { + if ($tmp['tag'] == $intopic['tag']) { + break; + } else { + $cnt ++; + } + } + if ($cnt == count($tag_intopic)) { + // not appear in $tag_intopic + array_push($tag_others, $tmp); + } + } + + // ----- + + + $data = array(); + //$data['taglistArray'] = $taglistArray; + $data['topic'] = $topic; + $data['topic_name'] = $topic_name; + + $data['tag_intopic'] = $tag_intopic; + $data['tag_others'] = $tag_others; + + return $data; + } + + + public function UpdateTagsInTopic($_postdata) { + $topic_id = $_postdata['topic_id']; + $tag_ids = json_decode(str_replace('\\', '', $_postdata['ids'])); + + // update topic_tag_relation by tags_ids array as `tag_id` and topic_id as `topic_id` + // --- add new topic_tag_relation --- + foreach ($tag_ids as $tag_id) { + $query = "SELECT * FROM topic_tag_relation WHERE tag_id=".$tag_id; + $result = mysql_query($query); + if (!$result) { + echo json_encode("error when select from topic_tag_relation"); + } + $topic_tag = array(); + $flag = false; + while ($row = mysql_fetch_assoc($result)) { + if ($row['topic_id'] == $topic_id) { + $flag = true; + break; + } + } + if (!$flag) { + // insert a row into topic_tag_relation table + $queryUpdate = "INSERT INTO topic_tag_relation (topic_id, tag_id) VALUES (".$topic_id.",".$tag_id.")"; + $resultUpdate = mysql_query($queryUpdate); + if (!$resultUpdate) { + return json_encode("error when insert topic_tag_relation table"); + } + } + + } + + // --- remove tags from this topic --- + $query = "SELECT * FROM topic_tag_relation WHERE topic_id=".$topic_id; + $result = mysql_query($query); + if (!$result) { + echo json_encode("error when select from topic_tag_relation"); + } + + while ($row = mysql_fetch_assoc($result)) { + $cnt = 0; + foreach ($tag_ids as $tag_id) { + if ($row['tag_id'] == $tag_id) { + break; + } else { + $cnt ++; + } + } + $_id = $row['id']; + if ($cnt == count($tag_ids)) { + // delete row with (topic_id, tag_ids) + $queryDelete = "DELETE FROM topic_tag_relation WHERE id=".$_id; + $resultDelete = mysql_query($queryDelete); + if (!$resultDelete) { + echo json_encode("error when delete from topic_tag_relation"); + } + } + } + + + + /* + $query = "SELECT * FROM topic_tag_relation"; + $result = mysql_query($query); + if (!$result) { + echo json_encode("error when select from topic_tag_relation"); + } + $topic_tag = array(); + while ($row = mysql_fetch_assoc($result)) { + array_push($topic_tag, array('tag_id'=>$row['tag_id'], 'topic_id'=>$row['topic_id'])); + } + + + foreach ($topic_tag as $value) { + $flag = false; + foreach ($tag_ids as $tag_id) { + if ($value['tag_id'] == $tag_id) { + //update its topic_id to $topic_id + $queryUpdate = "UPDATE topic_tag_relation SET topic_id=".$topic_id." WHERE tag_id=".$tag_id; + $resultUpdate = mysql_query($queryUpdate); + if (!$resultUpdate) { + return json_encode("error when update topic_tag_relation table"); + } + $flag = true; + break; + } + } + if (!$flag && $value['topic_id'] == $topic_id) { + // set its topic_id to 0, indicating unsigned + $queryUpdate = "UPDATE topic_tag_relation SET topic_id=0 WHERE tag_id=".$value['tag_id']; + $resultUpdate = mysql_query($queryUpdate); + if (!$resultUpdate) { + return json_encode("error when update topic_tag_relation table"); + } + } + } + */ + + } + + + private function GetTaglistByTopicID($topic_id) { + $taglistArray = array(); + // select taglist ids from topic_tag_relation table + $query = sprintf("SELECT * FROM `topic_tag_relation` WHERE `topic_id`='%s'", $topic_id); + $result = mysql_query($query); + if (!$result) { + return json_encode("Failed during selecting topic_tag_relation table."); + } + $taglist_ids = array(); + + while ($row = mysql_fetch_assoc($result)) { + array_push($taglist_ids, $row['tag_id']); + } + + // select taglist by tag ids + foreach ($taglist_ids as $tag_id) { + $query = sprintf("SELECT * FROM `taglist` WHERE `id`='%s'", $tag_id); + $result = mysql_query($query); + if (!$result) { + echo mysql_error(); + return json_encode("Failed during selecting taglist table."); + } + + $row = mysql_fetch_assoc($result); + array_push($taglistArray, array( $row['id'], $row['name'], $row['tag'], $row['color'] )); + + } + return $taglistArray; + } + + public function SetTopic($topic) { + $this->topic = $topic; + } + + public function GetTopic() { + return $this->topic; + } + + private function GetTopiclistArray() { + $topiclistArray = array(); + $result = $this->GetTopiclist(); + while ($row = mysql_fetch_assoc($result)) { + array_push($topiclistArray, array('id'=>$row['id'],'name'=>$row['name'],'tag'=>$row['tag'])); + } + return $topiclistArray; + } + + + private function GetTopicTag($topic_id) { + $result = $this->GetTopicByID($topic_id); + $row = mysql_fetch_assoc($result); + $tag = $row['tag']; + return $tag; + + } + private function GetTopicName($topic_id) { + $result = $this->GetTopicByID($topic_id); + $row = mysql_fetch_assoc($result); + $name = $row['name']; + return $name; + + } + + + // =========================== + + // === for manage wordlist === + public function EditWordlist() { + $result = $this->GetWordlist(); + $wordlistArray = array(); + while ($row = mysql_fetch_assoc($result)) { + $wordlistArray[$row['id']] = $row['name']; + } + + $data = array(); + $data['wordlistArray'] = $wordlistArray; + return $data; + } + + + public function AddNewList($postdata) { + if ($postdata['text']){ + if (get_magic_quotes_gpc()) { + $name = stripslashes($postdata['text']); + } else { + $name = $postdata['text']; + } + + $query1 = sprintf("INSERT INTO `wordlist` (`name`, `systemName`) VALUES (%s, %s)", + $this->GetSQLValueString($name, "text"), + $this->GetSQLValueString($this->systemNAME, "text")); + $result1 = mysql_query($query1); + file_put_contents( "data/wordlist/".mysql_insert_id().".txt", "(empty now)"); + } + } + + + public function SaveWordlist($postdata) { + + if ($postdata['text']){ + $date = date('Y_m_d_H_i_s', time()); + if ( file_exists("data/wordlist/".$postdata['filename'].".txt") ) { + $filename = "data/wordlist/".$postdata['filename']."_".$date.".txt"; + $oldFile = file_get_contents("data/wordlist/".$postdata['filename'].".txt"); + file_put_contents($filename, $oldFile); + } + /*else { + $filename = "data/wordlist/".$postdata['filename'].".txt"; + } + */ + + + if (get_magic_quotes_gpc()) { + $require = stripslashes($postdata['text']); + } else { + $require = $postdata['text']; + } + + $require = preg_replace("/<br>/u", "<br>", $require); + file_put_contents("data/wordlist/".$postdata['filename'].".txt", $require); + } + /* + if ($postdata['text']){ + $date = date('Y_m_d_H_i_s', time()); + if ( file_exists("data/wordlist/".$postdata['filename'].".txt") ) { + $oldFile = file_get_contents("data/wordlist/".$postdata['filename'].".txt"); + file_put_contents("data/wordlist/".$postdata['filename']."_".$date.".txt", $oldFile); + } + + if (get_magic_quotes_gpc()) { + $require = stripslashes($postdata['text']); + } else { + $require = $postdata['text']; + } + + // $require = preg_replace("/<br>/u", "", $require); + file_put_contents("data/wordlist/".$postdata['filename'].".txt", $require); + } + */ + } + + + // ======================================= + + public function sortFunction($a,$b) { + return strlen($b)-strlen($a); + } + + // TODO: delete this + private function SetSectionId($_urlvalues) { + // TODO: maybe get user info also + // get book id from url + if ($_urlvalues['id'] != "") { + $section_id = $_urlvalues['id']; + } else { + return json_encode("Error: No section id"); + /* ???? */ + /* + $get_book_id = $urlvalues['book']; + $get_start = $urlvalues['start']; + $get_end = $urlvalues['end']; + */ + } + $this->section_id = $section_id; + + } + + private function GetSectionId() { + + if (is_numeric($this->section_id)) { + return $this->section_id; + } else { + return json_encode("Error: No section id"); + } + } + + private function GetSectionInfo() { + $section_id = $this->GetSectionId(); + if (!is_numeric($section_id)){ + return $section_id; + } + + $result = $this->GetSectionsByID($section_id); + + + while ($row = mysql_fetch_assoc($result)) { + $bookId=$row['books_id']; + $startPage=$row['start_page']; + $endPage=$row['end_page']; + $sectionName = $row['name']; + } + + $data = array(); + $data['bookId'] = $bookId; + $data['startPage'] = $startPage; + $data['endPage'] = $endPage; + $data['sectionName'] = $sectionName; + + + return $data; + } + + private function ParseMetaData($filename) { + $text = file_get_contents($filename); + $xml = simplexml_load_string($text); //or die("Error: Cannot load from xml string"); + if (!$xml) { + // when file created by section_id, read the plain text from file_get_contents + return $text; + } + + $this->topic = (string)$xml->topic; // set topic id + + // get taglist in file + $taglist_infile = $xml->tagitem; + $taglistArray = array(); + foreach ($taglist_infile as $row) { + array_push($taglistArray, array((string)$row->id,(string)$row->name,(string)$row->tag,(string)$row->color )); + } + if ($taglistArray) { + $this->taglist_infile = $taglistArray; + } + + // get book meta data + $book_meta = $xml->book; + $book_metaArray = array(); + foreach ($book_meta as $row) { + //array_push($book_metaArray, array('title'=>(string)$row->title,'author'=>(string)$row->author,'year'=>(string)$row->year,'pagenumber'=>(string)$row->pagenumber )); + array_push($book_metaArray, array((string)$row->title,(string)$row->author,(string)$row->year,(string)$row->pagenumber )); + } + if ($book_metaArray) { + $this->book_meta = $book_metaArray; + } + + // echo $taglist->name.", ".$taglist->tag."," .$taglist->color; + // --- detect if the taglist set is up-to-date or not --- + $contentString = (string)$xml->text_content->asXML(); + //$removed_str = array("<text_content>","</text_content>"); + //$new_contentString = str_replace($removed_str, "", $contentString); + + return $contentString; + } + private function GetSectionContent() { + $section_id = $this->GetSectionId(); + $section_info = $this->GetSectionInfo(); + + $bookId = $section_info['bookId']; + $startPage = $section_info['startPage']; + $endPage = $section_info['endPage']; + + $contentString=""; + $data_path = $this->GetDataPath(); + if ( file_exists($data_path."parsing_files/".$section_id.".txt") ) { + $filename = $data_path."parsing_files/".$section_id.".txt"; + + // --- parsing meta data + $stringInput = $this->ParseMetaData($filename); + // ---- + + // if the text is from file system + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + } else { + $query = sprintf("SELECT `content`, `line`, `books_id` FROM `contents` WHERE `books_id`=\"%s\" AND `line`>=%d AND `line`<=%d", $bookId, $startPage, $endPage); + $result = mysql_query($query); + if (!$result) { + return json_encode("Failed during selecting content table."); + } + while ($row = mysql_fetch_assoc($result)) { + $contentString.="【".$row['line']."】".$row['content']."\n"; + } + + // the text is from database + $stringInput = $contentString; + $stringInput = preg_replace("/<(.*?)>/u", "○", $stringInput); + $stringInput = preg_replace("/ /u", "○", $stringInput); + $stringInput = preg_replace("/\n/u", "<br>", $stringInput); + $stringInput = preg_replace("/【(.*?)】/u", "【<a href=\"review_index_xml_images.php?books_id=".$bookId."&pages=\\1&entry=0\" target=\"_bookImg\">\\1</a>】", $stringInput); + } + + return $stringInput; + } + + private function GetDataPath() { + return getcwd()."/data/"; // get the current file path, which is getcwd(), and concatenate with "/data/" + } + + private function GetTaglistArray() { + $taglistArray = array(); + $result = $this->GetTaglist(); + while ($row = mysql_fetch_assoc($result)) { + array_push($taglistArray, array( $row['id'], $row['name'], $row['tag'], $row['color'] )); + } + + return $taglistArray; + } + + private function GetWordlistArray() { + $wordlistArray=""; + $result = $this->GetWordlist(); + while ($row = mysql_fetch_assoc($result)) { + $listString = file_get_contents("data/wordlist/".$row['id'].".txt"); + $listString = preg_replace("/<div>/u", "\n", $listString); + $listString = preg_replace("/<\/div>/u", "", $listString); + $listString = preg_replace("/<span(.*?)>/u", "", $listString); + $listString = preg_replace("/<\/span>/u", "", $listString); + //$listString = preg_replace("/\n/u", "|", $listString); + + $wordlistArray2 = explode( "\n", $listString ); + usort($wordlistArray2,'sortFunction'); + foreach ( $wordlistArray2 as $index=>$value ) { + $wordlistArray2[$index] = implode("○?", preg_split("/(?<!^)(?!$)/u", $value)); + } + foreach ( $wordlistArray2 as $index=>$value ) { + if ($value=="") unset($wordlistArray2[$index]); + + } + $listString = implode("|", $wordlistArray2); + + if ( $listString[0]=="|" ) $listString = substr($listString, 1); + $wordlistArray[] = array( $row['id'], $row['name'], $listString ); + } + + + return $wordlistArray; + + } + + protected function GetBooksInfo($bookId) { + $result = $this->GetSectionsByID($bookId); + while ($row = mysql_fetch_assoc($result)) { + $bookName = $row['name']; + } + + $data = array(); + $data['bookName'] = $bookName; + + return $data; + } + + +} + + + +?>